Preface
The main task of business intelligence (BI) is providing decision support for
business activities based on empirical information. The term business is understood
in a rather broad sense covering activities in different domain applications, for
example, an enterprise, a university, or a hospital. In the context of the business
under consideration, decision support can be at different levels ranging from the
operational support for a specific business activity up to strategic support at the top
level of an organization. Consequently, the term BI summarizes a huge set of models
and analytical methods such as reporting, data warehousing, data mining, process
mining, predictive analytics, organizational mining, or text mining.
In this book, we present fundamental ideas for a unified approach towards BI
activities with an emphasis on analytical methods developed in the areas of process
analysis and business analytics.
The general framework is developed in Chap. 1, which also gives an overview on
the structure of the book. One underlying idea is that all kinds of business activities
are understood as a process in time and the analysis of this process can emphasize
different perspectives of the process. Three perspectives are distinguished: (1)
the production perspective, which relates to the supplier of the business; (2) the
customer perspective, which relates to users/consumers of the offered business; and
(3) the organizational perspective, which considers issues such as operations in the
production perspective or social networks in the customer perspective.
Core elements of BI are data about the business, which refer either to the
description of the process or to instances of the process. These data may take
different views on the process defined by the following structural characteristics:
(1) an event view, which records detailed documentation of certain events; (2) a
state view, which monitors the development of certain attributes of process instances
over time; and (3) a cross-sectional view, which gives summary information of
characteristic attributes for process instances recorded within a certain period of
time.
The issues for which decision support is needed are often related to so-called
key performance indicators (KPIs) and to the understanding of how they depend on
certain influential factors, i.e., specificities of the business. For analytical purposes,
vii
viii
Preface
it is necessary to reformulate a KPI in a number of analytical goals. These goals
correspond to well-known methods of analysis and can be summarized under
the headings business description goals, business prediction goals, and business
understanding goals. Typical business description goals are reporting, segmentation
(unsupervised learning), and the identification of interesting behavior. Business prediction goals encompass estimation and classification and are known as supervised
learning in the context of machine learning. Business understanding goals support
stakeholders in understanding their business processes and may consist in process
identification and process analysis.
Based on this framework, we develop a method format for BI activities oriented
towards ideas of the L format for process mining and CRISP for business analytics.
The main tasks of the format are the business and data understanding task, the data
task, the modeling task, the analysis task, and the evaluation and reporting task.
These tasks define the structure of the following chapters.
Chapter 2 deals with questions of modeling. A broad range of models occur
in BI corresponding to the different business perspectives, a number of possible
views on the processes, and manifold analysis goals. Starting from possible ways
of understanding the term model, the most frequently used model structures in BI
are identified, such as logic-algebraic structures, graph structures, and probabilistic/statistical structures. Each structure is described in terms of its basic properties
and notation as well as algorithmic techniques for solving questions within these
structures. Background knowledge is assumed about these structures at the level of
introductory courses in programs for applied computer science. Additionally, basic
considerations about data generation, data quality, and handling temporal aspects
are presented.
Chapter 3 elaborates on the data provisioning process, ranging from data collection and extraction to a solid description of concepts and methods for transforming
data into analytical data formats necessary for using the data as input for the models
in the analysis. The analytical data formats also cover temporal data as used in
process analysis.
In Chap. 4, we present basic methods for data description and data visualization
that are used in the business and data understanding task as well as in the evaluation
and reporting task. Methods for process-oriented data and cross-sectional data are
considered. Based on these fundamental techniques, we sketch aspects of interactive
and dynamic visualization and reporting.
Chapters 5–8 explain different analytical techniques used for the main analysis
goals of supervised learning (prediction and classification), unsupervised learning
(clustering), as well as process identification and process analysis. Each chapter
is organized in such a way that we first present first an overview of the used
terminology and general methodological considerations. Thereafter, frequently used
analytical techniques are discussed.
Chapter 5 is devoted to analysis techniques for cross-sectional data, basically
traditional data mining techniques. For prediction, different regression techniques
are presented. For classification, we consider techniques based on statistical principles, techniques based on trees, and support vector machines. For unsupervised
Preface
ix
learning, we consider hierarchical clustering, partitioning methods, and modelbased clustering.
Chapter 6 focuses on analysis techniques for data with temporal structure. We
start with probabilistic-oriented models in particular, Markov chains and regressionbased techniques (event history analysis). The remainder of the chapter considers
analysis techniques useful for detecting interesting behavior in processes such as
association analysis, sequence mining, and episode mining.
Chapter 7 treats methods for process identification, process performance management, process mining, and process compliance. In Chap. 8, various analysis
techniques for problems are elaborated, which look at a business process from
different perspectives. The basics of social network analysis, organizational mining,
decision point analysis, and text mining are presented. The analysis of these
problems combines techniques from the previous chapters.
For explanation of a method, we use demonstration examples on the one hand
and more realistic examples based on use cases on the other hand. The latter include
the areas of medical applications, higher education, and customer relationship
management. These use cases are introduced in Chap. 1. For software solutions,
we focus on open source software, mainly R for cross-sectional analysis and ProM
for process analysis. A detailed code for the solutions together with instructions on
how to install the software can be found on the accompanying website:
www.businessintelligence-fundamentals.com
The presentation tries to avoid too much mathematical formalism. For the
derivation of properties of various algorithms, we refer to the corresponding
literature. Throughout the text, you will find different types of boxes. Light grey
boxes are used for the presentation of the use cases, dark grey boxes for templates
that outline the main activities in the different tasks, and white boxes for overview
summaries of important facts and basic structures of procedures.
The material presented in the book was used by the authors in a 4-h course on
Business Intelligence running for two semesters. In case of shorter courses, one
could start with Chaps. 1 and 2, followed by selected topics of Chaps. 3, 5, and 7.
Vienna, Austria
Vienna, Austria
Wilfried Grossmann
Stefanie Rinderle-Ma
http://www.springer.com/978-3-662-46530-1